bluemsi/2nd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: finalized wiki integrity maintenance (v3.0 standard) - pruned 1400+ stubs and fixed 11k+ ghost links

Browse Source
This commit is contained in:
Antigravity Agent
2026-05-02 09:18:34 +09:00
parent c84dcb8371
commit 6445fcc05b
13150 changed files with 55394 additions and 100862 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics_GD/Bellman Equation.md
+4 -4
View File
@@ -1,12 +1,12 @@
---
id: [[P-Reinforce]]-AI-BELLMAN
id: [[P-Reinforce|P-Reinforce]]-AI-BELLMAN
category: "10_Wiki/💡 Topics/AI"
confidence_score: 0.99
tags: [Bellman Equation, Reinforcement Learning, Math, Dynamic Programming]
last_reinforced: 2026-04-20
---
# [[Bellman-Equation]] (벨만 방정식)
# [[Bellman-Equation|Bellman-Equation]] (벨만 방정식)
## 📌 한 줄 통찰 (The Karpathy Summary)
> "오늘의 보상(Step reward) + 내일의 가치(Future value) = 오늘의 가치." 시간의 흐름 속에 흩어진 가치를 하나로 묶어주는 재귀의 미학이다.
@@ -23,5 +23,5 @@ last_reinforced: 2026-04-20
- 실제 세계(Model-free)에서는 다음 상태의 가치를 정확히 알 수 없다. 그래서 벨만 방정식을 기반으로 경험을 통해 가치를 추측해가는 'Q-Learning'이나 'Deep Q-Networks(DQN)'로 발전해왔다.
## 🔗 지식 연결 (Graph)
- Related: Reinforcement Learning , Deep-[[Reinforcement-Learning]]
- Foundation: [[Computational Theory & Math/Information Theory]]
- Related: Reinforcement Learning , Deep-[[Reinforcement-Learning|Reinforcement-Learning]]
- Foundation: Computational Theory & Math/Information Theory